SCOPE-BENCH shows state-of-the-art molecular models suffer up to 8x higher errors under extreme OOD, while POMA reduces mean absolute error by up to 11.2% via target-aware source selection and dual-scale adaptation.
Extended-connectivity fingerprints.Journal of chemical information and modeling, 50(5):742–754
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 5representative citing papers
A new method decomposes property differences between weakly related molecules into minimal chemical edits to train a directional evaluator that guides multi-step optimization with less oracle querying.
A new benchmarking framework shows virtual cell models overestimate performance on standard tests, drop sharply on unseen contexts and perturbations, and produce inconsistent rankings across metrics.
A systematic survey and benchmark of four deep learning paradigms for molecular property prediction that organizes the field, critiques current data practices, and outlines three future directions.
A neural network pipeline ranks plausible multistep metabolic pathways after training binary classifiers on real versus artificially generated reactions from public databases and enzymatic templates.
citing papers explorer
-
Rethinking Molecular OOD Generalization via Target-Aware Source Selection
SCOPE-BENCH shows state-of-the-art molecular models suffer up to 8x higher errors under extreme OOD, while POMA reduces mean absolute error by up to 11.2% via target-aware source selection and dual-scale adaptation.
-
From Single-Step Edit Response to Multi-Step Molecular Optimization
A new method decomposes property differences between weakly related molecules into minimal chemical edits to train a directional evaluator that guides multi-step optimization with less oracle querying.
-
Benchmarking virtual cell models for in-the-wild perturbation response
A new benchmarking framework shows virtual cell models overestimate performance on standard tests, drop sharply on unseen contexts and perturbations, and produce inconsistent rankings across metrics.
-
A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era
A systematic survey and benchmark of four deep learning paradigms for molecular property prediction that organizes the field, critiques current data practices, and outlines three future directions.
-
Computational framework for multistep metabolic pathway design
A neural network pipeline ranks plausible multistep metabolic pathways after training binary classifiers on real versus artificially generated reactions from public databases and enzymatic templates.